Long-range correlations and burstiness in written texts: Universal and language-specific aspects

Constantoudis, Vassilios; Diakonos, F. K.; Karamanos, Konstantinos; Papadimitriou, Constantinos; Chatzigeorgiou, Manolis; Papageorgiou, Harris

doi:10.1142/s0217979215410052

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result of a statistical analysis of a multi-language corpus of physicsrelated texts, Constantoudis et al (2015) demonstrated how the burstiness of long word appearances contributes more to the language-specific aspects of full-wordlength correlations. The authors concluded that the correlations between inter-long word distances are less sensitive to language dependencies.…”

Section: Perplexity and Burstiness In Written Textsmentioning

confidence: 99%

“AI, will you help?” How learners use Artificial Intelligence when writing

Krajka,

Olszak

2024

View full text Add to dashboard Cite

The current surge in the exploitation of Artificial Intelligence (AI) tools, accompanied by the subsequent rise in popularity of AI across different spheres of life, has unlocked a multitude of opportunities for students to employ diverse AI strategies to augment their process of learning. Drawing on the proliferation of Artificial Intelligence, the article examines the process of assisting academic writing instruction with an AI-enhanced word processor. The purpose of the paper is to investigate how successful advanced students are in determining whether an essay was written by AI tools or by a human and how much AI assistance they need to summarize, generate text and write from prompts when trained to use an AI-assisted word processor. The empirical data for the scientific investigation was obtained through a quasi-experimental treatment involving a single group of undergraduate applied linguistics students. The findings of this study indicate the high linguistic sensitivity of the research participants to factors regarding language and layout, which allows them to distinguish human authors from AI-powered texts. The current investigation possesses potential advantages for educators in the realm of foreign language acquisition and instruction, as they contemplate the strengths of their bilingual language learners within academic writing instruction.

show abstract

Section: Perplexity and Burstiness In Written Textsmentioning

confidence: 99%

“AI, will you help?” How learners use Artificial Intelligence when writing

Krajka,

Olszak

2024

View full text Add to dashboard Cite

show abstract

“…Several papers have used similar methods to map texts into token length sequences [24,[56][57][58][59]. The token length sequence mapping method (Eq.…”

Section: Token Length Sequence (Tls)mentioning

confidence: 99%

Enriching feature engineering for short text samples by language time series analysis

2020

View full text Add to dashboard Cite

In this case study, we are extending feature engineering approaches for short text samples by integrating techniques which have been introduced in the context of time series classification and signal processing. The general idea of the presented feature engineering approach is to tokenize the text samples under consideration and map each token to a number, which measures a specific property of the token. Consequently, each text sample becomes a language time series, which is generated from consecutively emitted tokens, and time is represented by the position of the respective token within the text sample. The resulting language time series can be characterised by collections of established time series feature extraction algorithms from time series analysis and signal processing. This approach maps each text sample (irrespective of its original length) to 3970 stylometric features, which can be analysed with standard statistical learning methodologies. The proposed feature engineering technique for short text data is applied to two different corpora: the Federalist Papers data set and the Spooky Books data set. We demonstrate that the extracted language time series features can be successfully combined with standard machine learning approaches for natural language processing and have the potential to improve the classification performance. Furthermore, the suggested feature engineering approach can be used for visualizing differences and commonalities of stylometric features. The presented framework models the systematic feature engineering based on approaches from time series classification and develops a statistical testing methodology for multi-classification problems.

show abstract

“…For example, co-occurrence networks might fail at capturing the relationship between distant words. Constantoudis et al (2015) reported that long-range correlations in written texts occur due to the multidimensional mapping of thoughts and ideas in chains of words. In order to account for the presence of relevant links between non-adjacent words, we proposed an extension called Further Neighborhood.…”

Section: Extensions Of Co-occurrence Networkmentioning

confidence: 99%

Development of new models for authorship recognition using complex networks

Marinho¹

View full text Add to dashboard Cite

Agradeço primeiramente a Deus pela vida cheia de alegrias, saúde e muitas oportunidades. Agradeço também à toda minha família. Principalmente aos meus pais, Sirlei e Dener, e minha irmã Isabela pelo amor, por serem meu porto seguro, e por sempre apoiarem os meus sonhos, principalmente o de estudar na USP. Ao meu orientador Dr. Diego Raphael Amancio por todos os ensinamentos, pela amizade, pela paciência e a disponibilidade em ajudar. Agradeço também pela liberdade que sempre me deu para realizar esse trabalho. I would like to express my sincere gratitude to Dr. Graeme Hirst, who accepted me in his research group and treated me as one of his students. Thank you so much! Ao meu namorado, amigo e confidente Fábio por todo o amor, carinho, apoio nas minhas decisões e pela ajuda em incontáveis momentos. Aos amigos e professores do NILC, em especial ao Edilson, Fernando, Leandro e Nathan. Aos colegas do IFSC, Henrique, Filipi e Prof. Luciano da F. Costa. Gostaria de agradecer também ao Prof. Francisco A. Rodrigues. Aos amigos que a USP me deu em 2009 e que a vida manteve, Débora e Leandro. Agradeço também às minhas amigas Mayara, Lívia, Vanessa L., Janine e Sheena por entenderem a minha ausência (e atrasos) em vários momentos. I'm also grateful to all the amazing friends I've made at the University of Toronto. Thank you so much Katie, Nona, and Patricia for making me feel welcome and for all the nice moments we've shared. Hope to see you all again someday. À FAPESP e a CAPES pelo apoio financeiro e pelo interesse nesse estudo. Ao ICMC e à USP por serem uma segunda casa nesses quase 9 anos.

show abstract

Long-range correlations and burstiness in written texts: Universal and language-specific aspects

Cited by 4 publications

References 21 publications

“AI, will you help?” How learners use Artificial Intelligence when writing

“AI, will you help?” How learners use Artificial Intelligence when writing

Enriching feature engineering for short text samples by language time series analysis

Development of new models for authorship recognition using complex networks

Contact Info

Product

Resources

About